AI Paper Atlas

Research map / Video / Action recognition

Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding

Xun Long Ng, Kian Eng Ong, Qichen Zheng, Yun Ni, Si Yong Yeo, Jun Liu

CVPR 2022 · Video › Action recognition · approach: Disentangled action recognition · 125 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add an approximated animal-specific feature alongside the general feature (ablation)CARe · Unseen animals action recognitionaccuracy (%): 27.3 -> 39.7Improved
Add a general feature alongside the approximated specific feature (ablation)CARe · Unseen animals action recognitionaccuracy (%): 38.2 -> 39.7Improved
Use spatially-aware tensor weights instead of scalar similarity weights (ablation)CARe · Unseen animals action recognitionaccuracy (%): 37.1 -> 39.7Improved
Use X3D with EQL instead of its cross-entropy baselineX3D · Animal Kingdom action recognitionoverall mAP: 25.25 -> 30.55Improved
Use X3D with LDAM-DRW instead of its cross-entropy baselineX3D · Animal Kingdom action recognitionoverall mAP: 25.25 -> 30.54Improved
Use X3D with Focal Loss instead of its cross-entropy baselineX3D · Animal Kingdom action recognitionoverall mAP: 25.25 -> 28.85Improved
Train with focal loss rather than cross-entropyI3D · Animal Kingdom action recognitionoverall mAP: 16.48 -> 26.49Improved
Train with focal loss rather than cross-entropySlowFast · Animal Kingdom action recognitionoverall mAP: 20.46 -> 24.74Improved
Use HRNet-DARK rather than HRNetAnimal Kingdom pose estimation, Protocol 1 · All speciesPCK@0.05: 66.06 -> 66.57Improved
Evaluate pose estimation on unseen animal subclasses rather than the mixed seen-class splitHRNet-DARK · Animal Kingdom pose estimationPCK@0.05: 66.57 -> 40.28Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy